Files
Qwen2.5-1.5B-Open-R1-Distill/all_results.json

8 lines
194 B
JSON
Raw Normal View History

{
"total_flos": 103624402944.0,
"train_loss": 0.0,
"train_runtime": 1.3161,
"train_samples": 93733,
"train_samples_per_second": 28.873,
"train_steps_per_second": 14.436
}